Papers by Zhao Cao
Agent-RewardBench: Towards a Unified Benchmark for Reward Modeling across Perception, Planning, and Safety in Real-World Multimodal Agents (2025.acl-long)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) are developing but lack external feedback . there is no clear on how to select reward models for agents . |
| Approach: | They propose a benchmark to evaluate agent reward modeling ability in MLLMs . they use multiple dimensions and real-world agent scenarios evaluation . |
| Outcome: | The proposed benchmark evaluates agent performance in multimodal large language models . it covers perception, planning, and safety with 7 scenarios and is highly difficult and high-quality . |
Thread: A Logic-Based Data Organization Paradigm for How-To Question Answering with Retrieval Augmented Generation (2025.emnlp-main)
Copied to clipboard
Kaikai An, Fangkai Yang, Liqun Li, Junting Lu, Sitao Cheng, Shuzheng Si, Lu Wang, Pu Zhao, Lele Cao, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Baobao Chang
| Challenge: | Recent advances in retrieval-augmented generation (RAG) have substantially improved question-answering systems, particularly for factoid ‘5Ws’ questions. |
| Approach: | They propose a data organization paradigm where large language models transform documents into more structured and loosely interconnected LUs. |
| Outcome: | Experiments in open-domain and industrial settings show that the proposed paradigm outperforms existing paradigms and shows high adaptability across diverse document formats. |
Head-wise Shareable Attention for Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) suffer from huge number of parameters, which restricts their deployment on edge devices. |
| Approach: | They propose two methods that share parameters across attention heads to reduce memory usage and reduce performance drop by using coarse-grained weight sharing rules. |
| Outcome: | The proposed methods reuse pre-trained weights without retraining and then share, denoted as PostShare. |
Event Ontology Completion with Hierarchical Structure Evolution Networks (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for event detection require predefined schemas, but manual defining is expensive and labor-intensive. |
| Approach: | They propose a task to achieve event clustering, hierarchy expansion and type naming . they propose 'neighbor Contrastive Clustering' module and a Hierarchy-Aware Linking module . |
| Outcome: | The proposed method outperforms baseline methods on three datasets. |
Unified Thinker: A General Reasoning Core for Image Generation (2026.acl-long)
Copied to clipboard
Sashuai Zhou, Qiang Zhou, Jijin Hu, Hanqing Yang, Yue Cao, Junpeng Ma, Yinchao Ma, Jun Song, Tiezheng Ge, Cheng Yu, Bo Zheng, Zhou Zhao
| Challenge: | generative models struggle with logic-intensive instruction following, exposing a persistent reasoning–execution gap. |
| Approach: | They propose a task-agnostic reasoning architecture for general image generation . they propose pixel-level feedback to ground the Thinker's policy in pixel feedback . |
| Outcome: | The proposed system significantly improves image reasoning and generation quality. |
LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing (2024.emnlp-main)
Copied to clipboard
Jiangshu Du, Yibo Wang, Wenting Zhao, Zhongfen Deng, Shuaiqi Liu, Renze Lou, Henry Zou, Pranav Narayanan Venkit, Nan Zhang, Mukund Srinath, Haoran Zhang, Vipul Gupta, Yinghui Li, Tao Li, Fei Wang, Qin Liu, Tianlin Liu, Pengzhi Gao, Congying Xia, Chen Xing, Cheng Jiayang, Zhaowei Wang, Ying Su, Raj Shah, Ruohao Guo, Jing Gu, Haoran Li, Kangda Wei, Zihao Wang, Lu Cheng, Surangika Ranathunga, Meng Fang, Jie Fu, Fei Liu, Ruihong Huang, Eduardo Blanco, Yixin Cao, Rui Zhang, Philip Yu, Wenpeng Yin
| Challenge: | a comparative analysis of paper (meta-)reviews by large language models (LLMs) aims to identify and distinguish LLMs from human activities . |
| Approach: | They present a comparative analysis to identify and distinguish LLM activities from human activities. |
| Outcome: | The proposed analysis aims to improve recognition of instances when someone implicitly uses LLMs for reviewing activities. |
AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation (2026.eacl-tutorials)
Copied to clipboard
| Challenge: | This tutorial provides an overview of recent advances in AI-assisted tools and models that support and enhance the scientific research process. |
| Approach: | This tutorial provides an overview of recent advances in AI-assisted tools and models that support and enhance the scientific research process. |
| Outcome: | This tutorial provides an overview of recent advances in AI-assisted tools and models that support and enhance the scientific research process. |
Continual Few-shot Event Detection via Hierarchical Augmentation Networks (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for continual few-shot event detection use labeled data, but in real-world applications, new event types emerge continually. |
| Approach: | They propose a memory-based framework for continual few-shot event detection . they incorporate prototypical augmentation into the memory set to memorize previous event types . |
| Outcome: | The proposed method outperforms existing methods in multiple continual few-shot event detection tasks. |
RippleCOT: Amplifying Ripple Effect of Knowledge Editing in Language Models via Chain-of-Thought In-Context Learning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | et al., 2022: ripple effect challenges knowledge editing for large language models. |
| Approach: | They propose a method to improve the accuracy of large language models by integrating Chain-of-Thought reasoning into the ICL editing approach. |
| Outcome: | RIPPLE-COT outperforms the state-of-the-art on the ripple effect, with gains ranging from 7.8% to 87.1%. |
LEGO: A Multi-agent Collaborative Framework with Role-playing and Iterative Feedback for Causality Explanation Generation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Causality explanation generation is a generative task that aims to explain why a given cause-effect pair is true using natural language. |
| Approach: | They propose a multi-agent framework with role-playing and iterative feedback for causality explanation generation. |
| Outcome: | The proposed framework is superior to existing frameworks on WIKIWHY and e-CARE datasets. |
MemoBrain: Executive Memory as an Agentic Brain for Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are inherently long-horizon, causing reasoning traces and tool artifacts to accumulate and strain the working context of large language models. |
| Approach: | They propose a model that constructs a dependency-aware memory over reasoning steps and captures salient intermediate states and their logical relations. |
| Outcome: | The proposed model prunes invalid steps, folds completed sub-trajectories, and preserves a compact, high-salience reasoning backbone under a fixed context budget. |
AWARE: Agentic Knowledge Warehousing for Contextual Intelligence (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models excel in information seeking tasks, but their knowledge is limited in coverage and timeliness. |
| Approach: | They propose an agentic knowledge warehousing framework that transforms unstructured data into minimal, task-conditioned knowledge representations consumable by LLMs. |
| Outcome: | Experiments on GAIA, WebWalker, and BrowseComp-Plus show improvements over baselines. |
Argue with Me Tersely: Towards Sentence-Level Counter-Argument Generation (2023.emnlp-main)
Copied to clipboard
Jiayu Lin, Rong Ye, Meng Han, Qi Zhang, Ruofei Lai, Xinyu Zhang, Zhao Cao, Xuanjing Huang, Zhongyu Wei
| Challenge: | Existing work describes paragraph-level counter-argument generation task as paragraph-based . however, sentence-level generation can be quite different due to its unique constraints and brevity-focused challenges. |
| Approach: | They propose a benchmark framework for sentence-level counter-argument generation . they use an annotated debate forum dataset to generate high-quality counter-argments . |
| Outcome: | The proposed framework and evaluator are competitive in counter-argument generation tasks. |
Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do (2026.acl-long)
Copied to clipboard
| Challenge: | Existing open-source models often yield only marginal overall improvements, possibly due to an overemphasis on mathematical reasoning at the expense of broader capabilities. |
| Approach: | They evaluate 12 multimodal tasks using 14 non-reasoning models and 8 reasoning models. |
| Outcome: | The proposed method is effective in multimodal reasoning tasks, the authors show . they show that it lacks the ability to maintain deep visual introspection throughout the reasoning process. |
WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing knowledge editing methods focus on single editing, failing to meet the requirements for lifelong editing. |
| Approach: | They propose an approach that selects editing layer based on the pattern matching degree of editing knowledge across different layers in language models. |
| Outcome: | The proposed method improves on GPT2-XL and GPT-J in lifelong editing compared to state-of-the-art methods . |
Unsupervised Dual Paraphrasing for Two-stage Semantic Parsing (2020.acl-main)
Copied to clipboard
| Challenge: | Existing semantic parsing frameworks rely on nontrivial human labor to generate canonical utterances. |
| Approach: | They propose a framework that uses an unsupervised paraphrase model to parse canonical utterances. |
| Outcome: | The proposed framework is effective and compatible with supervised training. |
Tug-of-War between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing knowledge conflicts in RALMs can ensnare them in a tug-of-war between knowledge and evidence, limiting their practical applicability. |
| Approach: | They propose a method called Conflict-Disentangle Contrastive Decoding (CD2) to better calibrate the model’s confidence. |
| Outcome: | The proposed method can resolve knowledge conflicts in large language models with the help of conflict-disentangle contrast decoding (CD2) . |
Beyond Polarity: Continuous Affect-Enhanced Multimodal Aspect-Based Sentiment Classification (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for multimodal aspect-based sentiment classification exploit discrete polarity patterns and generic visual embeddings. |
| Approach: | They propose a Valence–Arousal–Dominance(VAD)-Enhanced MABSC framework that integrates VAD signals into multimodal sentiment reasoning and learns emotion-sensitive image representations. |
| Outcome: | The proposed framework brings VAD signals into multimodal sentiment reasoning and learns emotion-sensitive image representations. |
Uncertain Local-to-Global Networks for Document-Level Event Factuality Identification (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies focus on identifying event factuality at sentence level, which leads to conflicts between different mentions of the same event. |
| Approach: | They propose a document-level event factuality identification model that uses local uncertainty and global structure to model event factuality. |
| Outcome: | The proposed method outperforms existing models on two widely used datasets. |
Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving (2025.emnlp-main)
Copied to clipboard
Chuxue Cao, Mengze Li, Juntao Dai, Jinluan Yang, Zijian Zhao, Shengyu Zhang, Weijie Shi, Chengzhong Liu, Sirui Han, Yike Guo
| Challenge: | Large language models (LLMs) have shown promising first-order logic (FOL) reasoning capabilities with applications in various areas, but their effectiveness in complex mathematical reasoning involving multi-step FOL deductions remains under-explored. |
| Approach: | They propose a self-adaptive solution that enhances the Diversity and REAsonability of LLMs’ generation strategies by introducing an Axiom-Driven Strategy Diversification mechanism and a Sub-Proposition Error Feedback to help LLM reflect on and correct their proofs. |
| Outcome: | The proposed model improves diversity and REAsonability of LLMs’ generation strategies by introducing an Axiom-Driven Strategy Diversification mechanism and a Sub-Proposition Error Feedback to help LLM reflect on and correct proofs. |
A Chain-of-Task Framework for Instruction Tuning of LLMs Based on Chinese Grammatical Error Correction (2025.coling-main)
Copied to clipboard
| Challenge: | Existing approaches to address Grammatical Error Correction (GEC) tasks are based on large scale labeled data, which leads to extremely high data annotation costs. |
| Approach: | They propose a Chain-of-Task framework to reduce over-correction in large language models . they propose supervised fine-tuning strategy and an algorithm for automatic dataset annotation . |
| Outcome: | The proposed framework achieves state-of-the-art on both FCGEC (in-domain) and NaCGEC (out-of domain) test sets. |
RetroMAE-2: Duplex Masked Auto-Encoder For Pre-Training Retrieval-Oriented Language Models (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for retrieval-oriented language models focus on contextualized embedding of the [CLS] token, but recent study shows that ordinary tokens besides [CLL] may provide extra information, which help to produce a better representation effect. |
| Approach: | They propose a method where all contextualized embeddings of pre-trained model can be jointly pre-trained for retrieval tasks. |
| Outcome: | The proposed method improves the quality of representation where all contextualized embeddings of the pre-trained model can be leveraged. |
CogKTR: A Knowledge-Enhanced Text Representation Toolkit for Natural Language Understanding (2022.emnlp-demos)
Copied to clipboard
Zhuoran Jin, Tianyi Men, Hongbang Yuan, Yuyang Zhou, Pengfei Cao, Yubo Chen, Zhipeng Xue, Kang Liu, Jun Zhao
| Challenge: | Existing knowledge-enhanced methods are limited to knowledge-intensive tasks. |
| Approach: | They propose a knowledge-enhanced text representation toolkit for natural language understanding . it combines knowledge acquisition, knowledge representation, knowledge injection and knowledge application . |
| Outcome: | The proposed toolkit supports knowledge acquisition, knowledge representation, knowledge injection, and knowledge application. |
Know-MRI: A Knowledge Mechanisms Revealer&Interpreter for Large Language Models (2025.acl-demo)
Copied to clipboard
Jiaxiang Liu, Boxuan Xing, Chenhao Yuan, ChenxiangZhang ChenxiangZhang, Di Wu, Xiusheng Huang, Haida Yu, Chuhan Lang, Pengfei Cao, Jun Zhao, Kang Liu
| Challenge: | Existing interpretation methods only support tasks with specific inputs, limiting their practical applications. |
| Approach: | They propose an extensible module that matches different input data with interpretation methods and consolidates the interpreting outputs. |
| Outcome: | The proposed module can match different input data with interpretation methods and consolidate the interpreting outputs. |
A Troublemaker with Contagious Jailbreak Makes Chaos in Honest Towns (2025.acl-long)
Copied to clipboard
| Challenge: | Existing research focuses on single-agent attacks and shared memory attacks, but real-world scenarios often involve independent memory. |
| Approach: | They propose a large-scale, multi-agent, multitopology attack evaluation framework that exploits the memory of an agent to make it more vulnerable to jailbreak attacks. |
| Outcome: | The proposed framework improves on the troublemaker makes chaos in Honest Town task with 23.51%, 18.95%, and 52.93% improvements in line, star topologies, and 100-agent settings. |
Bit-Flip Error Resilience in LLMs: A Comprehensive Analysis and Defense Framework (2025.emnlp-main)
Copied to clipboard
Yuhang Chen, Zhen Tan, Ajay Kumar Jaiswal, Huaizhi Qu, Xinyu Zhao, Qi Lin, Yu Cheng, Andrew Kwong, Zhichao Cao, Tianlong Chen
| Challenge: | Bit-flip errors (BFEs) are hardware faults where individual bits in memory or processing units are unintentionally flipped. |
| Approach: | They propose a novel defense strategy to mitigate bit-flip errors (BFEs) they propose bfe protection and a self-correction mechanism to minimize performance degradation . |
| Outcome: | The proposed defense strategy minimizes performance degradation while significantly improving robustness against BFEs. |
Towards Efficient NLP: A Standard Evaluation and A Strong Baseline (2022.naacl-main)
Copied to clipboard
Xiangyang Liu, Tianxiang Sun, Junliang He, Jiawen Wu, Lingling Wu, Xinyu Zhang, Hao Jiang, Zhao Cao, Xuanjing Huang, Xipeng Qiu
| Challenge: | Rather than pursuing the reachless SOTA accuracy, researchers are focusing on model efficiency and usability. |
| Approach: | They propose an evaluation and a public leaderboard for efficient NLP models that depicts the Pareto Frontier for various language understanding tasks. |
| Outcome: | The proposed model outperforms or performs on par with SOTA compressed and early exiting models. |
Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models (2024.findings-acl)
Copied to clipboard
Zhuoran Jin, Pengfei Cao, Hongbang Yuan, Yubo Chen, Jiexin Xu, Huaijun Li, Xiaojian Jiang, Kang Liu, Jun Zhao
| Challenge: | Existing methods to expand internal memory boundaries of language models by providing external context can often conflict, leading to knowledge conflicts. |
| Approach: | They propose a method that prunes conflicting attention heads without updating model parameters. |
| Outcome: | The proposed method can flexibly control eight LMs to use internal memory or external context without updating model parameters. |
Two Heads Are Better Than One: Improving Fake News Video Detection by Correlating with Neighbors (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing frameworks for detecting fake news videos are limited . a new approach is proposed to integrate neighborhood information of new videos . |
| Approach: | They propose a framework for automatically detecting fake news videos . it integrates neighborhood relationship of new videos belonging to same event . |
| Outcome: | The proposed framework improves performance of existing detectors and graph aggregation and debunking rectification modules. |
Focus on Your Question! Interpreting and Mitigating Toxic CoT Problems in Commonsense Reasoning (2024.acl-long)
Copied to clipboard
| Challenge: | Large language models exhibit high-level commonsense reasoning abilities, especially with enhancement methods like Chain-of-Thought (CoT). |
| Approach: | They propose a chain-of-thought-like method to elicit models' potential abilities to generate rationales and answers that are based on attribution tracing and causal tracers to probe the internal working mechanism of the LLM. |
| Outcome: | The proposed method eliminates Toxic CoT problems and improves the model’s overall commonsense reasoning performance by 5.5%. |
Hence, Socrates is mortal: A Benchmark for Natural Language Syllogistic Reasoning (2023.findings-acl)
Copied to clipboard
Yongkang Wu, Meng Han, Yutao Zhu, Lei Li, Xinyu Zhang, Ruofei Lai, Xiaoguang Li, Yuanhang Ren, Zhicheng Dou, Zhao Cao
| Challenge: | SylloBase is a benchmark for syllogistic reasoning, a critical capability widely required in natural language understanding tasks, such as text entailment and question answering. |
| Approach: | They propose to use a benchmark to learn syllogistic reasoning on a set of templates and to use them to generate and understand slogisms. |
| Outcome: | The proposed benchmark covers a complete taxonomy of syllogism reasoning patterns, and contains both automatically and manually constructed samples. |
Topology Matters: Measuring Memory Leakage in Multi-Agent LLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Multi-agent LLMs are rapidly moving from prototype to real-world use . network topology is a first-order security parameter in multi-aggent systems . |
| Approach: | They propose a framework for comparing topology-conditioned memory leakage in multi-agent LLM systems. |
| Outcome: | The proposed framework evaluates topology-conditioned memory leakage in multi-agent LLM systems. |
LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods to encode text-to-SQL data are node-centric and ignore semantics embedded in the topological structure of edges. |
| Approach: | They propose a Line Graph Enhanced Text-to-SQL model to mine relational features without constructing meta-paths. |
| Outcome: | The proposed model achieves state-of-the-art on the cross-domain text-to-SQL benchmark Spider at the time of writing. |
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing (2026.acl-industry)
Copied to clipboard
Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Zirui Tang, Boyu Niu, Yuanhong Zheng, Dongsheng Ma, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang, Fangdong Wang, Jingzhou Chen, Xiaomeng Zhao, Liqun Wei, Wei Li, Shasha Wang, RuiLiang Xu, Yuanyuan Cao, Lu Chen, Qianqian Wu, Huaiyu Gu, Lindong Lu, Dechen Lin, null Shenguanlin, Xuanhe Zhou, Linfeng Zhang, Yuhang Zang, Xiaoyi Dong, Jiaqi Wang, Bo Zhang, Lei Bai, Pei Chu, Weijia Li, Jiang Wu, Lijun Wu, Zhenxiang Li, Guangyu Wang, Zhongying Tu, Chao Xu, Kai Chen, Bowen Zhou, Dahua Lin, Wentao Zhang, Conghui He
| Challenge: | Document images are characterized by higher resolutions, denser content, and more complex structural layouts. |
| Approach: | They propose a 1.2B-parameter document parsing vision-language model that decouples layout analysis from local content recognition. |
| Outcome: | The proposed model surpasses general-purpose and domain-specific models on multiple benchmarks while maintaining significantly lower computational overhead. |
Robust Tool Use via Fission-GRPO: Learning to Recover from Execution Errors (2026.acl-long)
Copied to clipboard
Zhiwei Zhang, Fei Zhao, Rui Wang, Zezhong Wang, Bin Liang, Jiakang Wang, Yao Hu, Shaosheng Cao, Kam-Fai Wong
| Challenge: | Large language models (LLMs) can call tools effectively, but they remain brittle in multi-turn execution. |
| Approach: | They propose a framework that converts execution errors into on-policy corrective supervision within the RL training loop. |
| Outcome: | The proposed framework improves the error recovery rate of Qwen3-8B by 5.7% absolute and overall accuracy by 4.0% on BFCL v4 Multi-Turn. |
Sparse Activation Editing for Reliable Instruction Following in Narratives (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing benchmarks fail to capture the challenges of instruction following in complex narrative contexts. |
| Approach: | They propose a training-free framework that identifies and edits instruction-relevant neurons using only natural language instructions without requiring labelled data. |
| Outcome: | The proposed framework improves instruction following by identifying and editing instruction-relevant neurons using only natural language instructions, without requiring labelled data. |
TokenPenalty: Alleviating Attention Sinks and Positional Decay in LVLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Multimodal large language models (MLLMs) often hallucinate due to two relevant phenomena: massive activation phenomenon and positional information decay. |
| Approach: | They propose a token-level intervention strategy that dynamically suppresses irrelevant visual tokens while preserving key contextual signals. |
| Outcome: | Experiments show that TokenTruth significantly improves factual consistency across MLLMs on standard image understanding benchmarks. |
CoMoL: Efficient Mixture of LoRA Experts via Dynamic Core Space Merging (2026.findings-acl)
Copied to clipboard
Jie Cao, Zhenxuan Fan, Zhuonan Wang, Tianwei Lin, Ziyuan Zhao, Rolan Yan, Wenqiao Zhang, Feifei Shao, Hongwei Wang, Jun Xiao, Siliang Tang
| Challenge: | Existing PEFT methods suffer from limited parameter efficiency and coarse-grained adaptation due to proliferation of LoRA experts and instance-level routing. |
| Approach: | They propose a new MoE-LoRA framework that incorporates expert diversity, parameter efficiency, and fine-grained adaptation. |
| Outcome: | The proposed framework outperforms existing methods on multiple tasks while maintaining parameter efficiency. |
Interpreting Sentiment Composition with Latent Semantic Tree (2023.findings-acl)
Copied to clipboard
| Challenge: | Current researches on sentiment classification are shifting from improving model performance to interpretability. |
| Approach: | They propose a new tree form capable of interpreting sentiment composition in a principled way. |
| Outcome: | The proposed tree can explain sentiment composition in a principled way. |
MULFE: A Multi-Level Benchmark for Free Text Model Editing (2024.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have impressive capabilities in comprehending human language and vast parametric knowledge obtained from large corpora. |
| Approach: | They propose a multi-level benchmark for free text model editing to bridge the gap . they categorize probe queries into three levels of generalization . |
| Outcome: | The proposed method improves the generalization performance of large langugae models. |
TIE: Topological Information Enhanced Structural Reading Comprehension on Web Pages (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing models for structural reading comprehension (SRC) only focus on comprehension of plain text, tables, tables or knowledge bases. |
| Approach: | They propose a topological information enhanced model which transforms a token-level task into a tag-level one by introducing a two-stage process. |
| Outcome: | The proposed model outperforms baselines and achieves state-of-the-art performance on the web-based SRC benchmark WebSRC at the time of writing. |
ShadowGNN: Graph Projection Neural Network for Text-to-SQL Parser (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing semantic parsing models struggle to adapt to unseen database schemas . a new architecture, ShadowGNN, processes schemas at abstract and semantic levels . |
| Approach: | They propose a new architecture which processes schemas at abstract and semantic levels. |
| Outcome: | The proposed architecture outperforms state-of-the-art models on a text-to-sql benchmark . it uses domain-independent representations to extract logical linking between question and schema . |
Rethinking the Role of Entropy in Optimizing Tool-Use Behaviors for Large Language Model Agents (2026.acl-long)
Copied to clipboard
Zeping Li, Hongru Wang, Yiwen Zhao, Guanhua Chen, Yixia Li, Keyang Chen, Yixin Cao, Guangnan Ye, Hongfeng Chai, Zhenfei Yin
| Challenge: | Large language models excel in mathematical reasoning and multi-hop question answering tasks, but in long trajectories, agents often invoke tools excessively or inappropriately, increasing computation cost and derailing the reasoning process. |
| Approach: | They propose to use entropy reduction as a supervisory signal to reduce tool calls . they propose to design two reward strategies to address the needs of optimizing tool-use behavior. |
| Outcome: | The proposed reward strategies reduce tool calls by 72.07% and improve performance by 22.27%. |
PGPO: Enhancing Agent Reasoning via Pseudocode-style Planning Guided Preference Optimization (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing LLM agents generate verbose and inefficient natural language plans to guide reasoning, which restricts agents’ ability to generalize across similar tasks. |
| Approach: | They propose a pseudocode-style planning guide optimization method that captures the structural logic of reasoning and uses two planning-oriented rewards to enhance agent learning. |
| Outcome: | The proposed method outperforms existing LLM agents on representative agent benchmarks and outperformed the current leading baselines. |
MIMIR: A Customizable Agent Tuning Platform for Enhanced Scientific Applications (2024.emnlp-demo)
Copied to clipboard
Xiangru Tang, Chunyuan Deng, Hanminwang Hanminwang, Haoran Wang, Yilun Zhao, Wenqi Shi, Yi Fung, Wangchunshu Zhou, Jiannan Cao, Heng Ji, Arman Cohan, Mark Gerstein
| Challenge: | Large language models (LLMs) have evolved into interactive agents capable of planning, tool use, and task execution across various tasks. |
| Approach: | They propose a platform that leverages large language models to generate agent-tuning data for fine-tuneing smaller, specialized models. |
| Outcome: | MIMIR enables large models to simulate various roles and create interaction data, which can then be used to fine-tune open-source models like LLaMA2. |
ParaCook: On Time-Efficient Planning for Multi-Agent Systems (2026.findings-acl)
Copied to clipboard
Shiqi Zhang, Xinbei Ma, Yunqing Xu, Zouying Cao, Pengrui Lu, Haobo Yuan, Tiancheng Shen, Zhuosheng Zhang, Hai Zhao, Ming-Hsuan Yang
| Challenge: | Existing agent benchmarks focus on task completion while neglecting time efficiency in parallel and asynchronous operations. |
| Approach: | They propose a framework for large language models that allows agents to plan long-horizon tasks in a scalable way. |
| Outcome: | The proposed framework is based on the Overcooked game and can be used to evaluate time efficiency-aware multi-agent planning. |
LaCo: Large Language Model Pruning via Layer Collapse (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for model quantization, knowledge distillation, and model pruning are limited by hardware support limitations and the need for extensive training. |
| Approach: | They propose a layer-wise structured pruner that collapses rear model layers into a prior layer and enables a rapid reduction in model size while preserving the model structure. |
| Outcome: | The proposed pruner outperforms state-of-the-art pruning methods at pruning ratios of 25-30% and maintains an average task performance of over 80% at different pruning ratio. |
Enhancing Dialogue-based Relation Extraction by Speaker and Trigger Words Prediction (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for identifying relations from dialogues do not fully consider the particularity of dialogues, making them difficult to understand the semantics between conversational arguments. |
| Approach: | They propose two tasks to enhance the extraction of dialogue-based relations . speaker prediction captures the characteristics of speakerrelated entities . the trigger words prediction provides supportive contexts for relations between arguments . |
| Outcome: | The proposed tasks improve the extraction of dialogue-based relations . speaker prediction captures the characteristics of speakerrelated entities . the trigger words prediction provides supportive contexts for relations between arguments . |
HyperCore: Hyperbolic and Co-graph Representation for Automatic ICD Coding (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods for ICD coding ignore Code Hierarchy and Code Co-occurrence . cost of manual coding estimated to be $25 billion per year in the US . |
| Approach: | They propose a hyperbolic representation method to leverage the code hierarchy and a graph convolutional network to utilize the code co-occurrence. |
| Outcome: | The proposed model outperforms state-of-the-art methods on two widely used datasets. |
DialogUSR: Complex Dialogue Utterance Splitting and Reformulation for Multiple Intent Detection (2022.findings-emnlp)
Copied to clipboard
Haoran Meng, Zheng Xin, Tianyu Liu, Zizhen Wang, He Feng, Binghuai Lin, Xuemin Zhao, Yunbo Cao, Zhifang Sui
| Challenge: | DialogUSR is a plug-in and domain-agnostic module that empowers multi-intent detection for chatbots . a single user query triggers inquiries on highspeed train ticket price and weather of destination. |
| Approach: | They propose a dialog utterance splitting and reformulation task that splits multi-intent user query into multiple single-intention sub-queries and recovers all coreferred and omitted information in the sub-questions. |
| Outcome: | The proposed model can be used to split multi-intent user queries into multiple sub-queries . it can be trained in two stages and perform in-depth analyses on the proposed models . |
Incremental Summarization for Customer Support via Progressive Note-Taking and Agent Feedback (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Using a mixtral-87B model, we reduce the time it takes to generate concise notes during conversations, and reduce the amount of time spent on manual review. |
| Approach: | They propose a system that combines a Mixtral-87B model for continuous note generation with a DeBERTa-based classifier to filter trivial content. |
| Outcome: | The proposed system achieved a 3% reduction in case handling time compared to bulk summarization, and high agent satisfaction ratings from surveys. |
DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding (2026.findings-acl)
Copied to clipboard
| Challenge: | Autoregressive (AR) large audio language models are expensive in data and computation . prior work shows diffusion-based LALMs can improve audio understanding under matched settings . |
| Approach: | They propose a diffusion-based LALM that upgrades the speech encoder and employs dual semantic and acoustic adapters. |
| Outcome: | a new model improves over existing autoregressive large language models and is competitive to strong AR models . the proposed model can make use of limited training data and improve inference efficiency . a recent study shows that diffusion-based models can improve audio understanding . |
Whispers that Shake Foundations: Analyzing and Mitigating False Premise Hallucinations in Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models generate hallucinated text when confronted with false premise questions . authors propose a method to mitigate false premises hallucinosity . |
| Approach: | They propose a method to constrain false premise attention heads during the model inference process. |
| Outcome: | The proposed method improves performance by constraining false premise attention heads . it yields a notable increase of nearly 20% of model performance . |
LINKED: Eliciting, Filtering and Integrating Knowledge in Large Language Model for Commonsense Reasoning (2024.findings-emnlp)
Copied to clipboard
Jiachun Li, Pengfei Cao, Chenhao Wang, Zhuoran Jin, Yubo Chen, Kang Liu, Xiaojian Jiang, Jiexin Xu, Jun Zhao
| Challenge: | Large language models (LLMs) often exhibit poor performance on knowledge-intensive tasks, such as commonsense reasoning. |
| Approach: | They propose a method to elicit, filter and integrate knowledge in large language models (LINKED) they propose 'reward model' to filter out noisy knowledge and 'take marginal consistent reasoning module' |
| Outcome: | The proposed method outperforms SOTA baselines on two commonsense reasoning tasks. |
Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM Safety (2026.acl-long)
Copied to clipboard
Can Jin, Rui Wu, Tong Che, Qixin Zhang, Hongwu Peng, Jiahui Zhao, Zhenting Wang, Wenqi Wei, Ligong Han, Zhao Zhang, Yuan Cao, Ruixiang Tang, Dimitris N. Metaxas
| Challenge: | OpenAI introduces deliberative alignment (DA) to enhance safety of its o-series models, but effectiveness of this approach in open-source LLMs is understudied. |
| Approach: | They propose a case-augmented deliberative alignment method for large language models . they propose to use reinforcement learning on self-generated safety reasoning chains . |
| Outcome: | The proposed method avoids narrowly enumerated rules and allows broader adaptability. |
DiffusionSL: Sequence Labeling via Tag Diffusion Process (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Sequence Labeling (SL) is a long-standing field of natural language processing. |
| Approach: | They propose a framework that utilizes a conditional discrete diffusion model for generating discrete tag data. |
| Outcome: | The proposed framework outperforms gpt-3.5-turbo on multiple benchmark datasets and tasks. |
Effective Sequence-to-Sequence Dialogue State Tracking (2021.emnlp-main)
Copied to clipboard
| Challenge: | Using Sequence-to-Sequence models for dialogue state tracking remains an understudied topic. |
| Approach: | They propose to use a pre-training objective and a dialogue context representation to investigate this problem. |
| Outcome: | The proposed model is more effective than auto-regressive language modeling, the authors show . the proposed model may have a hard time recovering from earlier mistakes, they say . |
See the World, Discover Knowledge: A Chinese Factuality Evaluation for Large Vision Language Models (2025.findings-acl)
Copied to clipboard
Jihao Gu, Yingyao Wang, Pi Bu, Chen Wang, Ziming Wang, Tengtao Song, Donglai Wei, Jiale Yuan, Yingxiu Zhao, Yancheng He, Shilong Li, Jiaheng Liu, Meng Cao, Jun Song, Yingshui Tan, Xiang Li, Wenbo Su, Xiaoyong Zhu, Bo Zheng
| Challenge: | Existing models for large vision language models do not fully reflect their knowledge capacity and reliability, resulting in erroneous outputs that do not align with the image content or provide answers lacking knowledge evidence. |
| Approach: | They propose a Chinese-based benchmark for visual factuality across 8 major topics and 56 subtopics and a multi-hop question construction. |
| Outcome: | The proposed model decouples visual factuality into two parts: seeing the world and discovering knowledge. |
Line Graph Enhanced AMR-to-Text Generation with Mix-Order Graph Attention Networks (2020.acl-main)
Copied to clipboard
| Challenge: | Existing graph-to-sequence approaches use graph neural networks as encoders, but they lack the structure information needed to translate AMR into the graph-based data. |
| Approach: | They propose a graph-to-sequence task which aims to recover natural language from Abstract Meaning Representations (AMR) they adopt graph attention networks with higher-order neighborhood information to explore the edge relations in AMR graphs. |
| Outcome: | The proposed framework achieves state-of-the-art performance on English AMR benchmark datasets and is able to translate the AMR semantics into the natural language. |
I²B-LPO: Latent Policy Optimization via Iterative Information Bottleneck (2026.acl-long)
Copied to clipboard
Huilin Deng, Hongchen Luo, Yue Zhu, Long Li, Zhuoyue Chen, Xinghao Zhao, Ming LI, Chuyang Zhao, Jihai Zhang, MengChang Wang, Yang Cao, Yu Kang
| Challenge: | Existing methods for large language model reasoning suffer from exploration collapse due to the semantic homogeneity of random rollouts. |
| Approach: | They propose to use latent policy optimization via iterative information bottleneck to optimize reasoning trajectories by diversifying reasoning . |
| Outcome: | Empirical results show that the proposed method achieves state-of-the-art performance with margins of up to 5.3% in accuracy and 7.4% in diversity metrics. |
CLUE: A Chinese Language Understanding Evaluation Benchmark (2020.coling-main)
Copied to clipboard
Liang Xu, Hai Hu, Xuanwei Zhang, Lu Li, Chenjie Cao, Yudong Li, Yechen Xu, Kai Sun, Dian Yu, Cong Yu, Yin Tian, Qianqian Dong, Weitang Liu, Bo Shi, Yiming Cui, Junyi Li, Jun Zeng, Rongzhao Wang, Weijian Xie, Yanting Li, Yina Patterson, Zuoyu Tian, Yiwen Zhang, He Zhou, Shaoweihua Liu, Zhe Zhao, Qipeng Zhao, Cong Yue, Xinrui Zhang, Zhengliang Yang, Kyle Richardson, Zhenzhong Lan
| Challenge: | Existing language evaluation benchmarks for English are limited to English . lack of such benchmarks makes it difficult to replicate success in other languages . |
| Approach: | They introduce a large-scale Chinese language understanding evaluation benchmark . the benchmark uses a set of current state-of-the-art pre-trained Chinese models . |
| Outcome: | The first large-scale Chinese Language Understanding Evaluation (CLUE) benchmark is released . the benchmark evaluates models across a wide range of tasks on original Chinese text . existing language evaluation benchmarks are mostly limited to English . |
ZhuJiu: A Multi-dimensional, Multi-faceted Chinese Benchmark for Large Language Models (2023.emnlp-demo)
Copied to clipboard
Baoli Zhang, Haining Xie, Pengfan Du, Junhao Chen, Pengfei Cao, Yubo Chen, Shengping Liu, Kang Liu, Jun Zhao
| Challenge: | Various types of LLMs have recently been rapidly developing, such as Llama2 and ChatGLM2 . |
| Approach: | They propose a benchmark that comprehensively evaluates LLMs across 7 ability dimensions covering 51 tasks. |
| Outcome: | The proposed benchmarks are comprehensive and systematic, with a high level of accuracy and authority. |
IAG: Induction-Augmented Generation Framework for Answering Reasoning Questions (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to QA using retrieval-augmented knowledge are limited by limited coverage and noisy information. |
| Approach: | They propose an induction-augmented generation framework that utilizes inductive knowledge along with retrieved documents for implicit reasoning. |
| Outcome: | The proposed framework outperforms RAG and ChatGPT on two Open-Domain QA tasks. |
Learning How to Remember: A Meta-Cognitive Management Method for Structured and Transferable Agent Memory (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches store memory in fixed representations and reuse it at a single or implicit level of abstraction, which limits generalization and often leads to negative transfer when distribution shift. |
| Approach: | They propose a Meta-Cognitive Memory Abstraction method which decouples task execution from memory management by combining a frozen task model with a learned memory copilot. |
| Outcome: | Experiments on ALFWorld, ScienceWorld, and BabyAI show that the proposed method improves performance, out-of-distribution generalization, and cross-task transfer over several baselines. |
Attribution-Based Analysis and Optimization of Modular Agentic Workflows (2026.findings-acl)
Copied to clipboard
Yingxuan Yang, Bo Huang, Siyuan Qi, Chao Feng, Haoyi Hu, Yuxuan Zhu, Jinbo Hu, Haoran Zhao, Ziyi He, Xiao Liu, ZongYu Wang, Muning Wen, Lin Qiu, Xuezhi Cao, Xunliang Cai, Yong Yu, Weinan Zhang
| Challenge: | Large Language Models (LLMs) have driven the rise of agentic workflows . yet, how can we attribute performance gains to individual upgrades and their interactions? |
| Approach: | They propose a game-theoretic framework that models component upgrades as players and evaluates component coalitions to compute Shapley values. |
| Outcome: | The proposed framework provides interaction-aware attribution and recommendation for model allocation under a fixed workflow structure. |
ICLEval: Evaluating In-Context Learning Ability of Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Existing evaluation frameworks focus on language abilities and knowledge, often overlooking the assessment of ICL ability. |
| Approach: | They propose to evaluate the ICL ability of Large Language Models (LLMs) using the ICLEval benchmark. |
| Outcome: | The proposed benchmark demonstrates that ICL ability is universally present in different LLMs and model size is not the sole determinant of ICL efficacy. |
Sentiment Word Aware Multimodal Refinement for Multimodal Sentiment Analysis with ASR Errors (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing models for multimodal sentiment analysis are limited in their capacity to be deployed in the real world. |
| Approach: | They propose a model that can dynamically refine erroneous sentiment words by leveraging multimodal sentiment clues. |
| Outcome: | The proposed model surpasses the state-of-the-art models on three datasets. |
Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing frameworks treat memory as a static append-only archive . Existing systems focus on passive accumulation, resulting in a 'passive accumulation' of memory. |
| Approach: | They propose a framework for experience-driven agent evolution that integrates procedural memory with contextual information to create a high-quality experience pool. |
| Outcome: | Experiments on BFCL-V3 and AppWorld show that ReMe outperforms memoryless Qwen3-8B. |
Visual Prompt Tuning for Few-Shot Text Classification (2022.coling-1)
Copied to clipboard
| Challenge: | Existing work on pretraining models for text classification uses image encoders instead of visual prompts. |
| Approach: | They propose a method to deploy large-scale pre-trained models in the prompt-tuning paradigm in few-shot learning. |
| Outcome: | The proposed method outperforms the most recent prompt-tuning methods on five public text classification datasets. |
Leveraging Denoised Abstract Meaning Representation for Grammatical Error Correction (2023.findings-acl)
Copied to clipboard
| Challenge: | Popular GEC models use large-scale synthetic corpora or use a large number of human-designed rules. |
| Approach: | They propose a model that incorporates denoised AMR as additional knowledge to get AMRs more reliable. |
| Outcome: | The proposed model reduces training time by 32% while inference time is comparable. |
Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning (2026.acl-long)
Copied to clipboard
Yanrui Du, Fenglei Fan, Sendong Zhao, Jiawei Cao, Ming Ma, Danyang Zhao, Shuren Qi, Ting Liu, Bing Qin
| Challenge: | Instruction Fine-Tuning (IFT) has emerged as a critical technique for customizing Large Language Models (LLMs) however, recent studies have revealed that IFT can compromise the built-in security mechanisms of LLMs, posing significant security risks. |
| Approach: | They propose a method that shifts learning burden onto security-robust parameters and propose 'warm-up' phase that preferentially trains Mods_Rob to learn low-level features with minimal security risk. |
| Outcome: | The proposed method reduces security risks without sacrificing performance gains across knowledge-intensive datasets. |
Better Red Teaming via Searching with Large Language Model (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for evaluating large language models face challenges in managing semantic intricacies and optimizing the efficiency of the search process. |
| Approach: | They propose a framework that reconceptualizes test case generation as a strategic planning problem, leveraging Monte Carlo Tree Search. |
| Outcome: | Experiments on a range of LLM architectures show that the proposed framework achieves state-of-the-art attack success rates without sacrificing computational efficiency. |
Named Entity Recognition with Small Strongly Labeled and Large Weakly Labeled Data (2021.acl-long)
Copied to clipboard
| Challenge: | Existing work focuses on learning deep NER models with weak supervision without any human annotation. |
| Approach: | They propose a framework that can suppress the noise of the weak labels and fine-tune over the strongly labeled data. |
| Outcome: | The proposed framework outperforms existing methods on Named Entity Recognition tasks with weak supervision and weakly labeled data. |
Disentangling Language and Culture for Evaluating Multilingual Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Extensive evaluations of large language models (LLMs) are conducted on a wide range of models, revealing a notable cultural-linguistic synergy phenomenon, where models exhibit better performance when questions are culturally aligned with the language. |
| Approach: | They propose a Dual Evaluation Framework to comprehensively assess the multilingual capabilities of large language models by decomposing evaluation along dimensions of linguistic medium and cultural context. |
| Outcome: | The proposed framework allows for a nuanced analysis of LLMs’ ability to process questions within both native and cross-cultural contexts cross-lingually. |
Curr-ReFT: Overcoming Training Bottlenecks in Small-scale Vision-Language Models via Curriculum Reinforcement Finetuning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | State-of-the-art vision-language models require massive scaling that limits practical deployment. |
| Approach: | They propose to use supervised fine-tuning to train small-scale vision-language models but face out-of-domain collapse when trained with traditional supervised learning (SFT). |
| Outcome: | Experiments show that curr-reFT achieves state-of-the-art performance across visual tasks in both in- and out-of domain settings and benchmarks. |
Semantic Parsing for English as a Second Language (2020.acl-main)
Copied to clipboard
| Challenge: | Existing studies on domain adaptation in NLP focus on learning challenges at the syntax-semantics interface during second language acquisition. |
| Approach: | They propose to use English Resource Grammar and TLE to parse ESL data using a reranking model to evaluate the quality of the annotations. |
| Outcome: | The proposed model can obtain a very promising quality in comparison to human annotations. |
Show, Don’t Tell: Demonstrations Outperform Descriptions for Schema-Guided Task-Oriented Dialogue (2022.naacl-main)
Copied to clipboard
| Challenge: | Recent work has leveraged natural language descriptions of schema elements to enable universal dialogue systems; however, descriptions only indirectly convey schema semantics. |
| Approach: | They propose to use schema-guided modeling to prompt seq2seq models with a labeled example dialogue to show schema semantics rather than tell them. |
| Outcome: | The proposed model outperforms models using short examples as schema representations on two popular dialogue state tracking benchmarks. |
ZhuJiu-Knowledge: A Fairer Platform for Evaluating Multiple Knowledge Types in Large Language Models (2024.naacl-demo)
Copied to clipboard
| Challenge: | evaluating the knowledge of large language models (LLMs) is crucial, and rapid advancement in large language modeling has heightened the importance of model evaluations. |
| Approach: | They propose a fairer benchmark for evaluating multiple knowledge types of LLMs by focusing on commonsense knowledge, world knowledge, and language knowledge. |
| Outcome: | The proposed framework evaluates 14 current mainstream LLMs and provides a detailed discussion and analysis of their results. |
Hi-ArG: Exploring the Integration of Hierarchical Argumentation Graphs in Language Pretraining (2023.emnlp-main)
Copied to clipboard
Jingcong Liang, Rong Ye, Meng Han, Qi Zhang, Ruofei Lai, Xinyu Zhang, Zhao Cao, Xuanjing Huang, Zhongyu Wei
| Challenge: | Recent studies have discussed its capability to assist language models for various applications. |
| Approach: | They propose a structure to organize arguments using the **Hi**erarchical **Ar**gumentation **G**raph (Hi-ArG) and propose two approaches to exploit Hi-AarG, including a text-graph multi-modal model GreaseArR and a framework augmented with graph information. |
| Outcome: | The proposed structure supersedes existing language models on two argumentation tasks while incorporating graph information during further training improves vanilla language models. |
RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for dense retrieval are not effective, but there are still challenges. |
| Approach: | They propose a retrieval oriented pre-training paradigm based on Masked Auto-Encoder (MAE) where the sentence embedding is generated from the encoder’s masked input and the original sentence is recovered based upon the sentence embedded and decoded input via mangled language modeling. |
| Outcome: | The proposed model significantly improves the SOTA performance on a wide range of NLP benchmarks, like BEIR and MS MARCO. |
CQR-SQL: Conversational Question Reformulation Enhanced Context-Dependent Text-to-SQL Parsers (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing text-to-SQL methods focus on making full use of history context, but neglect to explicitly comprehend the schema and conversational dependency. |
| Approach: | They propose a CQR-SQL that explicitly exploits schema and conversational dependency for multi-turn SQL parsing. |
| Outcome: | The proposed method exploits schema and contextual dependency for multi-turn SQL parsing. |
LearnDA: Learnable Knowledge-Guided Data Augmentation for Event Causality Identification (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for event causality identification (ECI) rely on annotated training data. |
| Approach: | They propose a method to augment training data for event causality identification by iteratively generating new examples and classifying event causalities in a dual learning framework. |
| Outcome: | The proposed method outperforms existing methods on EventStoryLine and Causal-TimeBank. |
Vocabulary Pyramid Network: Multi-Pass Encoding and Decoding with Multi-Level Vocabularies for Response Generation (P19-1)
Copied to clipboard
| Challenge: | Conventional methods employ a fixed vocabulary and one-pass decoding, which make them prone to safe and general responses and lack further refinement to the first generated raw sequence. |
| Approach: | They propose a Vocabulary Pyramid Network which integrates multi-pass encoding and decoding with multi-level vocabularies into response generation. |
| Outcome: | The proposed system outperforms strong baselines on English Twitter and Chinese Weibo datasets. |
Domain-Lifelong Learning for Dialogue State Tracking via Knowledge Preservation Networks (2021.emnlp-main)
Copied to clipboard
Qingbin Liu, Pengfei Cao, Cao Liu, Jiansong Chen, Xunliang Cai, Fan Yang, Shizhu He, Kang Liu, Jun Zhao
| Challenge: | Existing offline DST models require a fixed dataset to train . Existing domain-lifelong learning methods are impractical in real-world applications . |
| Approach: | They propose a domain-lifelong learning method to continuously train a DST model on new data to learn incessantly emerging new domains while avoiding catastrophically forgetting old learned domains. |
| Outcome: | The proposed method outperforms state-of-the-art lifelong learning methods by 4.25% and 8.27% on the MultiWOZ and the SGD benchmarks. |
Word-level Cross-lingual Structure in Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated exceptional performance across a broad spectrum of cross-lingual Natural Language Processing (NLP) tasks. |
| Approach: | They propose to use Word-level Cross-lingual Structure to prove that the word-level embedding on the hidden layers isomorphic between languages. |
| Outcome: | The proposed method significantly improves on two representative LLM foundations, LLaMA2 and BLOOM. |
MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application (2026.acl-long)
Copied to clipboard
Xueqing Peng, Lingfei Qian, Yan Wang, Ruoyu Xiang, Yueru He, Yang Ren, Mingyang Jiang, Vincent Jim Zhang, Yuqing Guo, Jeff Zhao, Huan He, Yi Han, Yun Feng, Yuechen Jiang, Yupeng Cao, Haohang Li, Yangyang Yu, Xiaoyu Wang, Penglei Gao, Shengyuan Lin, Keyi Wang, Shanshan Yang, Yilun Zhao, Zhiwei Liu, Peng Lu, Jerry Huang, Suyuchen Wang, Triantafillos Papadopoulos, Polydoros Giannouris, Efstathia Soufleri, Nuo Chen, Zhiyang Deng, Heming Fu, Yijia Zhao, Mingquan Lin, Meikang Qiu, Kaleb E Smith, Arman Cohan, Xiao-Yang Liu, Jimin Huang, Guojun Xiong, Alejandro Lopez-Lira, Xi Chen, Junichi Tsujii, Jian-Yun Nie, Sophia Ananiadou, Qianqian Xie
| Challenge: | Existing evaluations of LLMs in finance are text-only, monolingual, and largely saturated by current models. |
| Approach: | They propose a multilingual and multimodal benchmark for evaluating LLMs in real financial contexts. |
| Outcome: | The first expert-annotated multilingual and multimodal benchmark is released . it evaluates 21 leading LLMs and shows they perform better in multilingual settings . |
UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter Efficient Fine-Tuning of Large Models (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods such as LoRA and VeRA use a low-rank approximation method that reduces the number of trainable parameters without compromising performance. |
| Approach: | They propose a parameter-efficient fine-tuning approach that leverages a low-rank approximation method that reduces the number of trainable parameters without compromising performance. |
| Outcome: | The proposed approach outperforms existing methods on GLUE and E2E benchmarks and is effective in instruction-tuning large language models and image classification models. |
Coarse-to-Fine: Hierarchical Multi-task Learning for Natural Language Understanding (2022.coling-1)
Copied to clipboard
Zhaoye Fei, Yu Tian, Yongkang Wu, Xinyu Zhang, Yutao Zhu, Zheng Liu, Jiawen Wu, Dejiang Kong, Ruofei Lai, Zhao Cao, Zhicheng Dou, Xipeng Qiu
| Challenge: | Existing methods to learn downstream tasks by stitches skill block lack rationality and interpretation. |
| Approach: | They propose a hierarchical framework with a coarse-to-fine paradigm for generalized text representations from the large-scale corpus. |
| Outcome: | The proposed model learns basic language properties from all tasks and boosts performance on relevant tasks. |
Unlocking the Future: Exploring Look-Ahead Planning Mechanistic Interpretability in Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have shown that large language models may possess preliminary planning capabilities. |
| Approach: | They examine the look-ahead planning mechanism in large language models from the perspectives of information flow and internal representations. |
| Outcome: | The proposed model can decode the decision from the output of MHSA in the middle layers at the last token. |
Cross-lingual Feature Extraction from Monolingual Corpora for Low-resource Unsupervised Bilingual Lexicon Induction (2022.coling-1)
Copied to clipboard
| Challenge: | Unsupervised bilingual lexicon induction models fail on low-resource language pairs due to insufficient initialization. |
| Approach: | They propose a method to learn cross-lingual features from monolingual corpora for low-resource UBLI by integrating cross-linguistic representations with pre-trained word embeddings in a fully unsupervised initialization. |
| Outcome: | The proposed method outperforms state-of-the-art methods on low-resource language pairs and improves representational ability and robustness of existing embedding models. |
Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models (2025.findings-naacl)
Copied to clipboard
| Challenge: | Text-to-image (T2I) models can be used to generate harmful content such as sexually explicit, unfaithful, and misleading or Not-Safe-for-Work (NSFW) images. |
| Approach: | They propose a more practical and universal attack that does not require the presence of a target model. |
| Outcome: | The proposed attack bypasses both text and image safety checkers while preserving high semantic alignment with the target prompt. |
OneEE: A One-Stage Framework for Fast Overlapping and Nested Event Extraction (2022.coling-1)
Copied to clipboard
| Challenge: | Event extraction (EE) is an essential task of information extraction, which aims to extract structured event information from unstructured text. |
| Approach: | They propose a tagging scheme and a model to form EE as word-word relation recognition using parallel grid tapping. |
| Outcome: | The proposed model achieves state-of-the-art on 3 overlapped and nested EE benchmarks and faster than baselines. |
Clinical-Coder: Assigning Interpretable ICD-10 Codes to Chinese Clinical Notes (2020.acl-demos)
Copied to clipboard
| Challenge: | Existing methods of automatic coding prediction have been successful, but the interpretability of predicted codes is a challenge. |
| Approach: | They propose an online system that can predict ICD codes for Chinese clinical notes by using a Dilated Convolutional Attention network with N-gram Matching mechanism. |
| Outcome: | The proposed system is able to provide supporting information in clinical decision making. |
Reinforcing Agentic Search Via Reward Density Optimization (2026.acl-long)
Copied to clipboard
| Challenge: | Reinforcement Learning with Verifiable Rewards (RLVR) is a promising approach for enhancing agentic search, but its performance is often hindered by reward sparsity . |
| Approach: | They propose a new research problem to improve the reward obtained per unit of exploration cost by using a system that decomposes long-horizon tasks into intermediate objectives and assigns process-level rewards to provide denser learning signals. |
| Outcome: | The proposed framework outperforms strong baselines on several agentic search benchmarks and achieves comparable performance to that of advanced proprietary models. |
Don’t Be Misled by Style: A Style-Adaptive Reranker for Capturing Effective Knowledge in Retrieval-Augmented Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing rerankers are mainly trained on well-edited texts, but stylistic features can be misled by reranked models. |
| Approach: | They propose a style-augmented multi-task framework that prioritizes effective knowledge over stylistic perturbations by using an LLM to derive passage-level supervision on whether a passage helps or harms answer correctness. |
| Outcome: | Extensive experiments show that SARK improves generation performance across multiple LLMs under mixed-style conditions. |
Towards Better Chain-of-Thought: A Reflection on Effectiveness and Faithfulness (2025.findings-acl)
Copied to clipboard
| Challenge: | Chain-of-thought (CoT) prompting demonstrates varying performance under different reasoning tasks. |
| Approach: | They propose to recall extra information from the question to enhance CoT generation and evaluate CoTs based on their information gain. |
| Outcome: | The proposed method improves both the faithfulness and effectiveness of CoT and evaluates it based on their information gain. |
Meeseeks: A Feedback-Driven, Iterative Self-Correction Benchmark evaluating LLMs’ Instruction Following Capability (2026.findings-acl)
Copied to clipboard
Jiaming Wang, Yunke Zhao, Peng Ding, Jun Kuang, Yibin Shen, Zhe Tang, Yilin Jin, ZongYu Wang, Xiaoyu Li, Xuezhi Cao
| Challenge: | Existing models lack the ability to adhere to instructions, resulting in suboptimal performance. |
| Approach: | They propose an automated iterative instruction-following benchmark with integrated feedback mechanism. |
| Outcome: | The proposed benchmark identifies erroneous components in model responses and provides feedback accurately. |
ConvTrans: Transforming Web Search Sessions for Conversational Dense Retrieval (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies show that conversational dense retrieval is a promising technique for realizing conversational search, but its implementation is severely hindered by the lack of data. |
| Approach: | They propose a method that transforms easily-accessible web search sessions into conversational search sessions to alleviate the data scarcity problem. |
| Outcome: | The proposed method can transform easily-accessible web search sessions into conversational search sessions. |
Incremental Event Detection via Knowledge Consolidation Networks (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to event detection require a fixed set of pre-defined event types . existing methods cannot handle semantic ambiguity and training data imbalance problems . |
| Approach: | They propose a Knowledge Consolidation Network to address these issues . they propose to use a prototype enhanced retrospection and hierarchical distillation to mitigate the adverse effects of semantic ambiguity and class imbalance. |
| Outcome: | The proposed method outperforms the state-of-the-art model by 19% and 13.4% of whole F1 score on ACE and TAC benchmarks. |
UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision (2026.acl-long)
Copied to clipboard
Zhen Fang, Ruiyan Han, XinYu Sun, Yuchen Ma, Ziheng Wang, Yu Zeng, Zehui Chen, Lin Chen, Wenxuan Huang, Wei-Jie Xu, Yi Cao, Feng Zhao
| Challenge: | Unified Multimodal Models have achieved remarkable success in cross-modal comprehension, but a gap persists in their ability to translate internal knowledge into faithful and controllable synthesis. |
| Approach: | They propose a self-improvement framework that partitions a single UMM into three collaborative roles: Proposer, Solver, and Judge. |
| Outcome: | The proposed framework improves on TIIF, DPG, CompBench and UniCycle benchmarks. |
Zero-Shot Cross-Lingual Document-Level Event Causality Identification with Heterogeneous Graph Contrastive Transfer Learning (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies focus on sentence-level ECI with high-resource languages, leaving document-level DECI with low-resourced languages under-explored. |
| Approach: | They propose a Heterogeneous Graph Interaction Model with Multi-granularity Contrastive Transfer Learning for zero-shot cross-lingual ECI. |
| Outcome: | The proposed model outperforms the state-of-the-art model on monolingual and multilingual scenarios by 9.4% and 8.2% of average F1 score. |
DORA: A Dual-Objective Reinforcement Learning Framework for Effective and Efficient Multimodal Agentic Search (2026.acl-long)
Copied to clipboard
Guangming Qin, Yuhao Deng, Yukun Zhao, Zhenyang Li, Junfeng Wang, Dawei Yin, Ye Yuan, Guoren Wang, Yizhou Yan, Chengliang Chai, Lei Cao
| Challenge: | Existing methods to train large language models overlook quality of intermediate search results . existing methods often invoke search calls during reasoning, making inference inefficient . |
| Approach: | They propose a dual-objective reinforcement learning framework to improve search strategies of MLLMs . DORA outperforms state-of-the-art methods, achieving up to 8.4% higher accuracy . |
| Outcome: | The proposed model outperforms state-of-the-art methods while reducing search calls by 9.7%. |
TARA: Token-level Attribute Relation Adaptation for Multi-Attribute Controllable Text Generation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work on multi-attribute controllable text generation ignores interrelations of attributes . recent work defines attribute relations as promotive, but not fixed . |
| Approach: | They propose a method that explicitly defines attribute relations as inhibtory for multi-attribute CTG . they propose 'tara' which employs token-level attribute relation adaptation and representation to generate text with the balanced multi-attribut . |
| Outcome: | The proposed method generates text with the balanced multi-attribute control. |
A + B: A General Generator-Reader Framework for Optimizing LLMs to Unleash Synergy Potential (2024.findings-acl)
Copied to clipboard
| Challenge: | Retrieval-Augmented Generation (RAG) is an effective solution to supplement necessary knowledge to large language models. |
| Approach: | They propose a "generate-then-read" pipeline to replace retrieval stage with generation from the LLM itself. |
| Outcome: | The proposed framework outperforms single models in the base and chat versions and addresses safety and helpfulness post-adaptation challenges. |
MIE: A Medical Information Extractor towards Medical Dialogues (2020.acl-main)
Copied to clipboard
| Challenge: | EMRs are important but many doctors suffer from writing them, which is time-consuming and tedious. |
| Approach: | They propose an automatic conversion of medical dialogues to EMRs using a window-sliding style . they propose a medical information extractor (MIE) that extracts medical information from medical dialogue . |
| Outcome: | The proposed model extracts medical information from doctor-patient dialogues. |
RedOne: Revealing Domain-specific LLM Post-Training in Social Networking Services (2025.emnlp-industry)
Copied to clipboard
Fei Zhao, Chonggang Lu, null Wangyue, Zheyong Xie, Ziyan Liu, Haofu Qian, Jianzhao Huang, Fangcheng Shi, Zijie Meng, Hongcheng Guo, Mingqian He, Xinze Lyu, Zheyu Ye, Weiting Liu, Boyang Wang, Shaosheng Cao
| Challenge: | Social networking services (SNS) have experienced rapid growth, which has proposed significant challenges for platform content management and interaction quality improvement. |
| Approach: | They propose a domain-specific LLM to break the performance bottleneck of single-task baselines and establish a comprehensive foundation for social networking services. |
| Outcome: | The proposed model achieves an average improvement of 14.02% across 8 major tasks and 7.56% in bilingual evaluation benchmark, compared with baseline models. |
Unveiling the Spectrum of Data Contamination in Language Model: A Survey from Detection to Remediation (2024.findings-acl)
Copied to clipboard
| Challenge: | Data contamination is a problem in Large language models due to the reliance on extensive internet-derived training corpora. |
| Approach: | They present a survey on the topic of data contamination in large language models. |
| Outcome: | The results of the first survey on data contamination in large language models provide a comprehensive guide for NLP researchers seeking a systematic understanding of the issue. |
Complex Event Schema Induction with Knowledge-Enriched Diffusion Model (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies on event schema induction have been hindered by errors and data quality issues. |
| Approach: | They propose a knowledge-enriched discrete diffusion model that distills event scenario knowledge from LLMs. |
| Outcome: | The proposed model achieves outstanding performance across evaluation metrics. |
Search-Oriented Conversational Query Editing (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing CQR models are not learned toward improving the downstream search performance . existing models generate the rewrite token-by-token from scratch . |
| Approach: | They propose a text editing-based CQR model tailored for conversational search . they propose rewrite tokens are selected from the dialogue in a non-autoregressive fashion . |
| Outcome: | The proposed model outperforms state-of-the-art models on three conversational search benchmarks while having low rewriting latency. |
Thinking Traps in Long Chain-of-Thought: A Measurable Study and Trap-Aware Adaptive Restart (2026.findings-acl)
Copied to clipboard
null Chenkang, Fan Yu, Junjie Nian, Sihan Zhao, Zhuoka Feng, Zijun Yao, Wang Heng, Yu Minshen, Yixin Cao
| Challenge: | Experiments show that extended generation does not guarantee correctness . a recurring pattern in Long-CoT failures is a problem for large reasoning models . |
| Approach: | They propose a test-time control framework that truncates the trajectory before the trap segment and adaptively restarts decoding. |
| Outcome: | Experiments show that TAAR improves reasoning performance without fine-tuning model parameters. |
Knowledge-Enriched Event Causality Identification via Latent Structure Induction Networks (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for identifying causal relations of events are limited . Existing approaches cannot handle well the problem, especially in the condition of lacking training data. |
| Approach: | They propose a Latent Structure Induction Network to integrate external structural knowledge into a causality reasoning task. |
| Outcome: | The proposed approach outperforms existing state-of-the-art methods on two widely used datasets. |
Automatic ICD Coding via Interactive Shared Representation Networks with Self-distillation Mechanism (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for ICD coding ignore the long-tail of code frequency or noisy clinical notes. |
| Approach: | They propose to use an interactive shared representation network to model code co-occurrences while focusing on the clinical note's noteworthy part and extract valuable information through a self-distillation learning mechanism to solve the long-tail problem. |
| Outcome: | The proposed model reduces the long-tail of code frequency and noise in clinical notes and extracts valuable information through a self-distillation learning mechanism. |
RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment (2025.findings-acl)
Copied to clipboard
Zhuoran Jin, Hongbang Yuan, Tianyi Men, Pengfei Cao, Yubo Chen, Jiexin Xu, Huaijun Li, Xiaojian Jiang, Kang Liu, Jun Zhao
| Challenge: | Existing retrieval augmented language models often overlook effective alignment with human preferences. |
| Approach: | They propose a benchmark to evaluate RMs in retrieval augmented language models . they incorporate 18 RAG subsets, six retrievers, and 24 RALMs to increase diversity . |
| Outcome: | The proposed benchmark combines 18 RAG subsets, six retrievers, and 24 RALMs to increase diversity of data sources. |
DTELS: Towards Dynamic Granularity of Timeline Summarization (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing timeline summarizations lack flexibility to meet diverse granularity needs . a fine-grained timeline showing the technical details is preferred for news topics . |
| Approach: | They propose a new paradigm to construct adaptive timelines based on user instructions or requirements. |
| Outcome: | The proposed timelines are informative and granularly consistent, but they struggle to generate consistent timelines. |
From Signal Degradation to Computation Collapse: Uncovering the Two Failure Modes of LLM Quantization (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing research on PTQ spans three primary directions. |
| Approach: | They conduct a systematic analysis of post-training quantization failures using PTQ . they show that targeted repair can mitigate Signal Degradation but remains ineffective for Computation Collapse . |
| Outcome: | The proposed method mitigates Signal Degradation but remains ineffective for Computation Collapse. |
Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning (2026.acl-long)
Copied to clipboard
| Challenge: | Multimodal web agents are cost-efficient and privacy-preserving, but suffer from weak planning and limited cross-website generalization. |
| Approach: | They propose a method which autonomously explores environments to discover experiences and utilizes hindsight experience to synthesize strictly aligned, high-level training data. |
| Outcome: | The proposed method outperforms Qwen2.5-VL-32B model on real-world benchmarks and demonstrates that mastering low-level atomic skills does not guarantee high-level planning competence. |
Enhancing Multiple-choice Machine Reading Comprehension by Punishing Illogical Interpretations (2021.emnlp-main)
Copied to clipboard
| Challenge: | Multiple-choice MRC is one of the most studied tasks in MRC due to the convenience of evaluation and the flexibility of answer format. |
| Approach: | They propose to use multiple-choice MRC to explain a trained model and reveal how it arrives at the prediction by punishing illogical attributions. |
| Outcome: | The proposed method improves model performance without external information and model structure change without any external information. |
Task-Stratified Knowledge Scaling Laws for Post-Training Quantized Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing scaling laws focus on general performance, overlooking crucial fine-grained factors and how quantization differentially impacts diverse knowledge capabilities. |
| Approach: | They propose a framework that unifies model size, bit-width, and fine-grained factors into memorization, application, and reasoning. |
| Outcome: | The proposed framework shows strong fit and cross-architecture consistency on 293 different PTQ configurations. |
InstructoR: Instructing Unsupervised Conversational Dense Retrieval with Large Language Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for conversational retrieval only fine-tune on limited supervised data, making it difficult for the retriever to fully grasp the entire conversation. |
| Approach: | They propose a method to instruct unsupervised conversational dense retrieval with large language models (LLMs) they use supervised data to discover the user's query intent from the conversation context . |
| Outcome: | The proposed method can bring significant improvements across various ad-hoc retrievers, surpassing the current state-of-the-art method. |
LESA: Learnable LLM Layer Scaling-Up (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for depth scaling-up rely on empirical heuristic rules for layer duplication, resulting in poor initialization and slower convergence during continual pre-training. |
| Approach: | They propose a method for learning latent parameters between layers by concatenating parameters from each layer and applying Singular Value Decomposition. |
| Outcome: | Experiments show that LESA outperforms baseline models with less than half the cost of existing methods. |
Alignment Precedes Fusion: Open-Vocabulary Named Entity Recognition as Context-Type Semantic Matching (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Continual learning and zero-shot learning approaches have not been adopted to scale to novel-emerging types. |
| Approach: | They propose a method to recognize entities in novel types by their textual names or descriptions. |
| Outcome: | The proposed method outperforms the state-of-the-art methods on three challenging OVNER benchmarks by 9.7%, 9.5%, and 1.8% F1-score of novel types. |
Enhancing Label Correlation Feedback in Multi-Label Text Classification via Multi-Task Learning (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to multi-task learning fail to capture label correlations . Existing methods suffer from label order dependency, label combination over-fitting and error propagation problems. |
| Approach: | They propose a novel approach with multi-task learning to enhance label correlation feedback. |
| Outcome: | The proposed method outperforms baselines on AAPD and RCV1-V2 datasets. |
Cracking Factual Knowledge: A Comprehensive Analysis of Degenerate Knowledge Neurons in Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) are believed to store extensive factual knowledge, yet the mechanisms of knowledge storage in LLMs remain largely unexplored. |
| Approach: | They propose that some multi-layer perceptron neurons can store "knowledge". |
| Outcome: | The proposed model can store "knowledge" in multi-layer perceptron neurons, but not redundancy. |
Revealing the Deceptiveness of Knowledge Editing: A Mechanistic Analysis of Superficial Editing (2025.acl-long)
Copied to clipboard
| Challenge: | Existing knowledge editing algorithms are prone to generating original knowledge . despite the fact that many models achieve near-perfect performance, superficial editing remains a challenge . |
| Approach: | They propose to use "**superficial editing**" to describe the phenomenon . they investigate the internal mechanisms of the attention module and their corresponding left singular vectors . |
| Outcome: | The proposed method can modify specific knowledge in a pretrained large language model while ensuring that unrelated knowledge remains unaffected. |
Relaxing the Constraints: A Dual-Importance Projection Mechanism for Lifelong Model Editing (2026.findings-acl)
Copied to clipboard
Zhenghai Chen, Senbin Xu, Jiaxi Tan, Xinhua Wu, Yan Zhang, Xiawu Zheng, Shengchuan Zhang, Ke Li, Sicheng Zhao, Liujuan Cao, Rongrong Ji
| Challenge: | Existing knowledge editing methods rely on strict orthogonal projection to preserve previously edited knowledge, but this constraint limits gradient expressiveness, resulting in degradation of model generalization and overall performance as the number of edits increases. |
| Approach: | They propose a method that leverages Singular Value Decomposition to identify critical gradient subspaces and introduces a dual mechanism comprising "accumulated importance" and "projection importance" |
| Outcome: | Extensive experiments on five mainstream LLMs show that the proposed method achieves an average comprehensive performance improvement of 10.36% and effectively maintains the model’s general capabilities on downstream tasks. |
Lightweight Haar Wavelet Subband Pruning for LLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have impressive performance but require computational and memory resources. |
| Approach: | They propose a post-training framework that uses a Haar wavelet transform to prune weights. |
| Outcome: | The proposed pruning framework reduces pruning time and computational costs by removing less important weights while preserving model architecture. |
A Good Neighbor, A Found Treasure: Mining Treasured Neighbors for Knowledge Graph Entity Typing (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to infer missing types for knowledge graphs only leverage one-hop neighbor information of the central entity, ignoring multi-hop neighbors that can provide valuable clues for inference. |
| Approach: | They propose a method to infer missing types for knowledge graph entities by using neighbor information and co-occurrence relations between types. |
| Outcome: | The proposed method significantly outperforms existing state-of-the-art methods on two widely used datasets. |
Improving Event Causality Identification via Self-Supervised Representation Learning on External Causal Statement (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for event causality identification (ECI) rely on labeled data, but the scale of annotated datasets is limited. |
| Approach: | They propose a self-supervised framework to learn context-specific causal patterns from external causal statements and adopt a contrastive transfer strategy to incorporate the learned context- specific causal patterns into the target ECI model. |
| Outcome: | The proposed method significantly outperforms existing methods on EventSto-ryLine and Causal-TimeBank (+2.0 and +3.4 points on F1 value respectively). |
AgentsCourt: Building Judicial Decision-Making Agents with Court Debate Simulation and Legal Knowledge Augmentation (2024.findings-emnlp)
Copied to clipboard
Zhitao He, Pengfei Cao, Chenhao Wang, Zhuoran Jin, Yubo Chen, Jiexin Xu, Huaijun Li, Kang Liu, Jun Zhao
| Challenge: | Recent advances in deep learning have significantly impacted the legal domain. |
| Approach: | They propose a multi-agent framework for judicial decision-making that simulates the court trial process . they propose 420 Chinese judgment documents to support their framework and build a large-scale legal knowledge base . |
| Outcome: | The proposed framework outperforms existing methods in various aspects, especially in generating legal articles. |
M2Edit: Locate and Edit Multi-Granularity Knowledge in Multimodal Large Language Model (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing knowledge editing methods for MLLMs lack multi-granularity knowledge . existing knowledge editing approaches lack multimodality knowledge and generalize to multimodal data. |
| Approach: | They propose a multimodal knowledge editing method which integrates key knowledge layers within MLLMs and collaboratively edits them. |
| Outcome: | The proposed method improves visual generality performance on knowledge data of different granularities. |
AnyTOD: A Programmable Task-Oriented Dialog System (2023.emnlp-main)
Copied to clipboard
Jeffrey Zhao, Yuan Cao, Raghav Gupta, Harrison Lee, Abhinav Rastogi, Mingqiu Wang, Hagen Soltau, Izhak Shafran, Yonghui Wu
| Challenge: | a neuro-symbolic approach allows zero-shot adaptation to unseen tasks and domains . a neural LM keeps track of events that occur during a conversation and a symbolic program implements dialog policy is executed to recommend actions. |
| Approach: | They propose an end-to-end, zero-shot task-oriented dialog system . it is designed to adapt to unseen tasks or domains without prior training . |
| Outcome: | The proposed system can be programmed to adapt to unseen tasks without training . it reduces data collection and training requirements for enabling new TOD 1 16189 tasks . |
Generative Calibration for In-context Learning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | In-context learning is one of the most exciting features of large language models . performance is sensitive to various configurations of the prompt, such as the choice or order of the training examples. |
| Approach: | They propose to calibrate the in-context predictive distribution by adjusting the label marginal . they find that the proposed method outperforms the ICL and state-of-the-art calibration methods . |
| Outcome: | The proposed method outperforms state-of-the-art methods by 27% absolute in macro-F1. |
Plug-and-Play Document Modules for Pre-trained Models (2023.acl-long)
Copied to clipboard
Chaojun Xiao, Zhengyan Zhang, Xu Han, Chi-Min Chan, Yankai Lin, Zhiyuan Liu, Xiangyang Li, Zhonghua Li, Zhao Cao, Maosong Sun
| Challenge: | Large-scale pre-trained models have been widely adopted for document-oriented NLP tasks, such as question answering. |
| Approach: | They propose to decouple document encoding from downstream tasks by introducing a document plugin into the backbone of a PTM. |
| Outcome: | The proposed model can encode documents once and for all across different scenarios. |
SSP: Self-Supervised Post-training for Conversational Search (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to search for information are limited by data scarcity and lack contextual semantic understanding. |
| Approach: | They propose a new post-training paradigm with three self-supervised tasks to initialize the conversational search model to enhance dialogue structure and contextual semantic understanding. |
| Outcome: | The proposed method can initialize the conversational search model to enhance dialogue structure and contextual semantic understanding. |
Generating Questions for Knowledge Bases via Incorporating Diversified Contexts and Answer-Aware Loss (D19-1)
Copied to clipboard
| Challenge: | Conventional methods for question generation neglect two crucial research issues: 1) the given predicate needs to be expressed; 2) the answer to the generated question needs to have a definitive answer. |
| Approach: | They propose a neural encoder-decoder model with multi-level copy mechanisms to generate questions . they also introduce answer-aware loss to make generated questions correspond to more definitive answers. |
| Outcome: | The proposed model achieves state-of-the-art performance while corresponding to more definitive answers. |
EvoWiki: Evaluating LLMs on Evolving Knowledge (2025.acl-long)
Copied to clipboard
Wei Tang, Yixin Cao, Yang Deng, Jiahao Ying, Bo Wang, Yizhe Yang, Yuyue Zhao, Qi Zhang, Xuanjing Huang, Yu-Gang Jiang, Yong Liao
| Challenge: | Existing knowledge evolution benchmarks are static and fail to capture the evolving nature of LLMs and knowledge. |
| Approach: | They propose an evolving dataset that categorizes information into stable, evolved, and uncharted states. |
| Outcome: | The proposed dataset is auto-updatable and enables evaluation of continuously changing knowledge and newly released LLMs. |
DPWriter: Reinforcement Learning with Diverse Planning Branching for Creative Writing (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for enhancing large language models (LLMs) lack explicit mechanisms for guiding diverse exploration and instead prioritize efficiency and performance over diversity. |
| Approach: | They propose a reinforcement learning-based framework that decomposes the generation process into explicitly planned intermediate steps and introduces divergence at the planning phase based on diversity variation. |
| Outcome: | The proposed method significantly outperforms existing baselines on creative writing benchmarks on a semi-structured long chain-of-thought (CoT) it introduces divergence at the planning phase based on diversity variation, alongside a group-aware diversity reward to encourage distinct trajectories. |
Adversarial Transfer Learning for Chinese Named Entity Recognition with Self-Attention Mechanism (D18-1)
Copied to clipboard
| Challenge: | Existing methods for named entity recognition (NER) do not exploit word boundary information from CWS or cannot filter the specific information of CWS. |
| Approach: | They propose to exploit task-shared boundary information to make full use of Chinese NER task and Chinese word segmentation (CWS) . |
| Outcome: | The proposed model significantly outperforms other state-of-the-art methods on two widely used datasets. |
Evaluating Personalized Tool-Augmented LLMs from the Perspectives of Personalization and Proactivity (2025.acl-long)
Copied to clipboard
| Challenge: | Personalized tool utilization is essential for aligning large language models (LLMs) with user preference in interaction scenarios with various tools. |
| Approach: | They propose a key-point-based LLM evaluation method that mitigates biases by manually annotating key points for each test case and providing them to LLM as the reference. |
| Outcome: | The proposed method mitigates biases in the LLM-as-a-judge system by manually annotating key points for each test case and providing them to LLM as the reference. |
Hyperlink-induced Pre-training for Passage Retrieval in Open-domain Question Answering (2022.acl-long)
Copied to clipboard
Jiawei Zhou, Xiaoguang Li, Lifeng Shang, Lan Luo, Ke Zhan, Enrui Hu, Xinyu Zhang, Hao Jiang, Zhao Cao, Fan Yu, Xin Jiang, Qun Liu, Lei Chen
| Challenge: | Existing methods to train dense passage retrieval have a large data gap between upstream and downstream relevance. |
| Approach: | They propose a method to pre-train the dense retriever with the text relevance induced by hyperlinks within Web documents. |
| Outcome: | The proposed method outperforms existing methods under different scenarios and in the open-domain question answering domain. |
Leros: Learning Explicit Reasoning on Synthesized Data for Commonsense Question Answering (2024.lrec-main)
Copied to clipboard
Chenhao Wang, Pengfei Cao, Jiachun Li, Yubo Chen, Kang Liu, Xiaojian Jiang, Jiexin Xu, Li Qiuxia, Jun Zhao
| Challenge: | Recent work shows large language models can generate useful rationales for commonsense question answering (CQA) however, the cost of deployment and further tuning is relatively expensive for the large models. |
| Approach: | They propose a framework that leverages both knowledge graphs and large language models to synthesize rationale-augmented CQA data. |
| Outcome: | The proposed model can generate useful rationales on unseen CQA benchmarks. |
LDEDE: LRP-Driven Efficient Detection and Editing Framework for LLM Privacy Neurons (2026.findings-acl)
Copied to clipboard
Zhao Zhengyuan, Cao Lifeng, null Sunhaodong, Shi Haotian, Du Xuehui, Liu Aodi, Niu Lanjie, Yang Xiaocheng
| Challenge: | Existing privacy protection methods fail to cover context-dependent sensitive information and are prone to performance degradation. |
| Approach: | They propose a Layer-wise Relevance Propagation-driven framework for efficient privacy neuron detection and editing. |
| Outcome: | The proposed framework achieves 80% higher efficiency than gradient attribution methods while reducing leakage risks of Phone, Email, and medical privacy by 42.7%–73.5% on average and cutting computational time by 60%–90%. |
Mobile-R1: Towards Interactive Capability for VLM-Based Mobile Agent via Systematic Training (2026.acl-long)
Copied to clipboard
Jihao Gu, Qihang Ai, Yingyao Wang, Pi Bu, Jingxuan Xing, Yue Cao, Zekun Zhu, Wei Jiang, Ziming Wang, Yingxiu Zhao, Ming-Liang Zhang, Jun Song, Yuning Jiang, Bo Zheng
| Challenge: | Existing approaches to training agents for visual-language models trap them in local optima, hindering exploration and error correction with the environment. |
| Approach: | They propose a hierarchical training recipe that bridges atomic action execution and strategic task completion. |
| Outcome: | The proposed training recipe bridges atomic action execution and strategic task completion. |
Representative Demonstration Selection for In-Context Learning with Two-Stage Determinantal Point Process (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods tend to select different demonstrations for each test instance, which is time-consuming and poses limitations in practical scenarios. |
| Approach: | They propose to select a representative subset of in-context demonstrations that can prompt different test instances in a specific task. |
| Outcome: | The proposed method can be used to generate representative in-context demonstrations. |
The Knowledge Microscope: Features as Better Analytical Lenses than Neurons (2025.acl-long)
Copied to clipboard
| Challenge: | Recent studies have shown that features are superior analytical units for understanding factual knowledge in Language Models. |
| Approach: | They propose a feature-based editing method that decomposes neurons into features rather than neurons to understand the mechanisms of factual knowledge in Language Models. |
| Outcome: | The proposed method demonstrates superior performance over neuron-based approaches in erasing privacy-sensitive information from LMs. |
PaperScope: A Multi-Modal Multi-Document Benchmark for Agentic Deep Research Across Massive Scientific Papers (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks focus on single-document understanding, whereas real scientific workflows require integrating evidence from multiple papers. |
| Approach: | They propose a multi-modal multi-document benchmark for agentic deep research that integrates evidence from multiple documents. |
| Outcome: | Experimental results show that even advanced systems achieve limited scores on PaperScope . paper provides a rigorous benchmark alongside a pipeline for constructing large multi-modal, multi-source deep research datasets. |